MRI图像偏置场矫正（bias field correction）

MR scans often display intensity non-uniformities due to variations in the magnetic field. So, one part of an image might appear lighter or darker when visualized, solely because of variations in the magnetic field. The map of these variations is called the bias field. The bias field can cause problems for a classifier as the variations in signal intensity are not due to any anatomical differences. ANTs N4 Bias Field Correctionattempts to correct the bias field by extracting it from the image.

#-*-coding:utf-8-*-
import os
import shutil
import SimpleITK as sitk
import warnings
import glob
import numpy as np
from nipype.interfaces.ants import N4BiasFieldCorrection


def correct_bias(in_file, out_file, image_type=sitk.sitkFloat64):
    """
    Corrects the bias using ANTs N4BiasFieldCorrection. If this fails, will then attempt to correct bias using SimpleITK
    :param in_file: nii文件的输入路径
    :param out_file: 校正后的文件保存路径名
    :return: 校正后的nii文件全路径名
    """
    # 使用N4BiasFieldCorrection校正MRI图像的偏置场
    correct = N4BiasFieldCorrection()
    correct.inputs.input_image = in_file
    correct.inputs.output_image = out_file
    try:
        done = correct.run()
        return done.outputs.output_image
    except IOError:
        warnings.warn(RuntimeWarning("ANTs N4BIasFieldCorrection could not be found."
                                     "Will try using SimpleITK for bias field correction"
                                     " which will take much longer. To fix this problem, add N4BiasFieldCorrection"
                                     " to your PATH system variable. (example: EXPORT PATH=${PATH}:/path/to/ants/bin)"))
        input_image = sitk.ReadImage(in_file, image_type)
        output_image = sitk.N4BiasFieldCorrection(input_image, input_image > 0)
        sitk.WriteImage(output_image, out_file)
        return os.path.abspath(out_file)

def normalize_image(in_file, out_file, bias_correction=True):
    # bias_correction：是否需要校正
    if bias_correction:
        correct_bias(in_file, out_file)
    else:
        shutil.copy(in_file, out_file)
    return out_file

最后

以上就是自由哈密瓜为你收集整理的MRI图像偏置场矫正（bias field correction）的全部内容，希望文章能够帮你解决MRI图像偏置场矫正（bias field correction）所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。